© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 813
    Prev
    Next
    INDEX
    Explanations

    string , metadata type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquette
    1.67
    
    1.62
     দারিদ্র
    1.59
    Ｈ
    1.55
    ার্জ
    1.53
     月
    1.51
    学院
    1.50
     DELL
    1.49
     hxg
    1.48
    ഷ്ണ
    1.47
    POSITIVE LOGITS
     tap
    1.59
     עי
    1.59
     mina
    1.43
    Unt
    1.41
    susp
    1.36
    withTrashed
    1.35
     pip
    1.33
    啧
    1.33
    underbrace
    1.33
    inject
    1.33
    Activations Density 0.323%

    No Known Activations